Great Service! Fine-grained Parsing of Implicit Arguments
- URL: http://arxiv.org/abs/2106.02561v1
- Date: Fri, 4 Jun 2021 15:50:35 GMT
- Title: Great Service! Fine-grained Parsing of Implicit Arguments
- Authors: Ruixiang Cui, Daniel Hershcovich
- Abstract summary: We show that certain types of implicit arguments are more difficult to parse than others.
This work will facilitate a better understanding of implicit and underspecified language, by incorporating it holistically into meaning representations.
- Score: 7.785534704637891
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Broad-coverage meaning representations in NLP mostly focus on explicitly
expressed content. More importantly, the scarcity of datasets annotating
diverse implicit roles limits empirical studies into their linguistic nuances.
For example, in the web review "Great service!", the provider and consumer are
implicit arguments of different types. We examine an annotated corpus of
fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully
re-annotating it, resolving several inconsistencies. Subsequently, we present
the first transition-based neural parser that can handle implicit arguments
dynamically, and experiment with two different transition systems on the
improved dataset. We find that certain types of implicit arguments are more
difficult to parse than others and that the simpler system is more accurate in
recovering implicit arguments, despite having a lower overall parsing score,
attesting current reasoning limitations of NLP models. This work will
facilitate a better understanding of implicit and underspecified language, by
incorporating it holistically into meaning representations.
Related papers
- ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR
Back-Translation [59.91139600152296]
ParaAMR is a large-scale syntactically diverse paraphrase dataset created by abstract meaning representation back-translation.
We show that ParaAMR can be used to improve on three NLP tasks: learning sentence embeddings, syntactically controlled paraphrase generation, and data augmentation for few-shot learning.
arXiv Detail & Related papers (2023-05-26T02:27:33Z) - Multi-resolution Interpretation and Diagnostics Tool for Natural
Language Classifiers [0.0]
This paper aims to create more flexible model explainability summaries by segments of observation or clusters of words that are semantically related to each other.
In addition, we introduce a root cause analysis method for NLP models, by analyzing representative False Positive and False Negative examples from different segments.
arXiv Detail & Related papers (2023-03-06T22:59:02Z) - SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers [61.48159785138462]
This paper aims to improve the performance of text-to-dependence by exploring the intrinsic uncertainties in the neural network based approaches (called SUN)
Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms competitors and achieves new state-of-the-art results.
arXiv Detail & Related papers (2022-09-14T06:27:51Z) - Argumentative Explanations for Pattern-Based Text Classifiers [15.81939090849456]
We focus on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification.
We propose AXPLR, a novel explanation method using (forms of) computational argumentation to generate explanations.
arXiv Detail & Related papers (2022-05-22T21:16:49Z) - Infusing Finetuning with Semantic Dependencies [62.37697048781823]
We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models.
We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
arXiv Detail & Related papers (2020-12-10T01:27:24Z) - Aspect-Based Argument Mining [2.3148470932285665]
We present the task of Aspect-Based Argument Mining (ABAM) with the essential subtasks of Aspect Term Extraction (ATE) and Nested Term Extraction (NS)
We consider aspects as the main point(s) argument units are addressing.
This information is important for further downstream tasks such as argument ranking, argument summarization and generation, as well as the search for counter-arguments on the aspect-level.
arXiv Detail & Related papers (2020-11-01T21:57:51Z) - Pareto Probing: Trading Off Accuracy for Complexity [87.09294772742737]
We argue for a probe metric that reflects the fundamental trade-off between probe complexity and performance.
Our experiments with dependency parsing reveal a wide gap in syntactic knowledge between contextual and non-contextual representations.
arXiv Detail & Related papers (2020-10-05T17:27:31Z) - Deep Learning for Abstract Argumentation Semantics [3.759936323189418]
We present a learning-based approach to determining acceptance of arguments under several abstract argumentation semantics.
We propose an argumentation graph neural network (AGNN) that learns a message-passing algorithm to predict the likelihood of an argument being accepted.
arXiv Detail & Related papers (2020-07-15T11:37:28Z) - Refining Implicit Argument Annotation for UCCA [6.873471412788333]
This paper proposes a typology for fine-grained implicit argument annotation on top of Universal Cognitive Conceptual's foundational layer.
The proposed implicit argument categorisation is driven by theories of implicit role interpretation and consists of six types: Deictic, Generic, Genre-based, Type-identifiable, Non-specific, and Iterated-set.
arXiv Detail & Related papers (2020-05-26T17:24:15Z) - pyBART: Evidence-based Syntactic Transformations for IE [52.93947844555369]
We present pyBART, an easy-to-use open-source Python library for converting English UD trees to Enhanced UD graphs or to our representation.
When evaluated in a pattern-based relation extraction scenario, our representation results in higher extraction scores than Enhanced UD, while requiring fewer patterns.
arXiv Detail & Related papers (2020-05-04T07:38:34Z) - Aspect-Controlled Neural Argument Generation [65.91772010586605]
We train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect.
Our evaluation shows that our generation model is able to generate high-quality, aspect-specific arguments.
These arguments can be used to improve the performance of stance detection models via data augmentation and to generate counter-arguments.
arXiv Detail & Related papers (2020-04-30T20:17:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.